Conditional Image Generation with Score-Based Diffusion Models
Conditional Image Generation with Score-Based Diffusion Models
复制标题
DOI：
--
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Georgios Batzolis;Jan Stanczuk;C. Schonlieb;Christian Etmann
中科院分区：
文献类型：
--
作者：
Georgios Batzolis;Jan Stanczuk;C. Schonlieb;Christian Etmann
基于分数的扩散模型已经成为深度生成模型的最有前途的框架之一。在这项工作中，我们对基于分数的扩散模型学习条件概率分布的不同方法进行了系统的比较和理论分析。特别地，我们证明了为条件分数的最成功估计之一提供理论证明的结果。此外，我们引入了一个多速度扩散框架，这导致了一个新的条件分数估计器，其性能与以前的最先进方法相当。我们的理论和实验结果伴随着一个开源的库MSDiff，它允许应用和进一步研究多速度扩散模型。
Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical analysis of different approaches to learning conditional probability distributions with score-based diffusion models. In particular, we prove results which provide a theoretical justification for one of the most successful estimators of the conditional score. Moreover, we introduce a multi-speed diffusion framework, which leads to a new estimator for the conditional score, performing on par with previous state-of-the-art approaches. Our theoretical and experimental findings are accompanied by an open source library MSDiff which allows for application and further research of multi-speed diffusion models.